{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5KZBKWEJL3AJIHS5YUDU7EBUXF","short_pith_number":"pith:5KZBKWEJ","canonical_record":{"source":{"id":"2302.08268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-16T12:54:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"981c5fa19af49f0c48e872b2f4f3b1e985edeb177f8f8eb1d78ffb7d208ecef0","abstract_canon_sha256":"25275409cad505860cbf8a507141a74f6d3aaaa9e1c48ea7ccee83ae14135eeb"},"schema_version":"1.0"},"canonical_sha256":"eab21558895ec0941e5dc5074f9034b948d5bc85ef7d7b43e9f36339c66fdc63","source":{"kind":"arxiv","id":"2302.08268","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08268","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08268v1","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08268","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"5KZBKWEJL3AJ","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"pith_short_16","alias_value":"5KZBKWEJL3AJIHS5","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"pith_short_8","alias_value":"5KZBKWEJ","created_at":"2026-07-05T05:42:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5KZBKWEJL3AJIHS5YUDU7EBUXF","target":"record","payload":{"canonical_record":{"source":{"id":"2302.08268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-16T12:54:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"981c5fa19af49f0c48e872b2f4f3b1e985edeb177f8f8eb1d78ffb7d208ecef0","abstract_canon_sha256":"25275409cad505860cbf8a507141a74f6d3aaaa9e1c48ea7ccee83ae14135eeb"},"schema_version":"1.0"},"canonical_sha256":"eab21558895ec0941e5dc5074f9034b948d5bc85ef7d7b43e9f36339c66fdc63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:36.219894Z","signature_b64":"i/0xEoUU9wJ4R18tbWAvb2s77eUYlCYLIjivi4zT/LikHEHR3xAChVIF6QDjblyDVWdpHG6Y2x1+gJYzdvhEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eab21558895ec0941e5dc5074f9034b948d5bc85ef7d7b43e9f36339c66fdc63","last_reissued_at":"2026-07-05T05:42:36.219464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:36.219464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.08268","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AqU1ixebn0Hw18N8SGQlBw7ujqdi65d8evRnFwFAjP808QJxyejmqr7sJnj1qS9X/sjJUDx8UwFKFlyGvfknAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:37:28.763543Z"},"content_sha256":"60447171100e63c91f1d793c80ebe61d21efba7b17c724616d26139d54721674","schema_version":"1.0","event_id":"sha256:60447171100e63c91f1d793c80ebe61d21efba7b17c724616d26139d54721674"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5KZBKWEJL3AJIHS5YUDU7EBUXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval-augmented Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bruno Martins, Desmond Elliott, Rita Ramos","submitted_at":"2023-02-16T12:54:13Z","abstract_excerpt":"Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08268","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.08268/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLZ+9KyBts713Xv0RzSxsM7b+4IBhxRxRRplT+GiXo36YXmkXH8EmotiBWJRFZGsMkZgF+73efQ0Il/LwTU9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:37:28.764351Z"},"content_sha256":"d22ff0ae5fe4d9cafaf95351d8a5fd2a0f5be439122a3bc67fea1c930f01ceea","schema_version":"1.0","event_id":"sha256:d22ff0ae5fe4d9cafaf95351d8a5fd2a0f5be439122a3bc67fea1c930f01ceea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5KZBKWEJL3AJIHS5YUDU7EBUXF/bundle.json","state_url":"https://pith.science/pith/5KZBKWEJL3AJIHS5YUDU7EBUXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5KZBKWEJL3AJIHS5YUDU7EBUXF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T18:37:28Z","links":{"resolver":"https://pith.science/pith/5KZBKWEJL3AJIHS5YUDU7EBUXF","bundle":"https://pith.science/pith/5KZBKWEJL3AJIHS5YUDU7EBUXF/bundle.json","state":"https://pith.science/pith/5KZBKWEJL3AJIHS5YUDU7EBUXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5KZBKWEJL3AJIHS5YUDU7EBUXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5KZBKWEJL3AJIHS5YUDU7EBUXF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"25275409cad505860cbf8a507141a74f6d3aaaa9e1c48ea7ccee83ae14135eeb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-16T12:54:13Z","title_canon_sha256":"981c5fa19af49f0c48e872b2f4f3b1e985edeb177f8f8eb1d78ffb7d208ecef0"},"schema_version":"1.0","source":{"id":"2302.08268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08268","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08268v1","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08268","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"5KZBKWEJL3AJ","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"pith_short_16","alias_value":"5KZBKWEJL3AJIHS5","created_at":"2026-07-05T05:42:36Z"},{"alias_kind":"pith_short_8","alias_value":"5KZBKWEJ","created_at":"2026-07-05T05:42:36Z"}],"graph_snapshots":[{"event_id":"sha256:d22ff0ae5fe4d9cafaf95351d8a5fd2a0f5be439122a3bc67fea1c930f01ceea","target":"graph","created_at":"2026-07-05T05:42:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.08268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be ef","authors_text":"Bruno Martins, Desmond Elliott, Rita Ramos","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-16T12:54:13Z","title":"Retrieval-augmented Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08268","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:60447171100e63c91f1d793c80ebe61d21efba7b17c724616d26139d54721674","target":"record","created_at":"2026-07-05T05:42:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"25275409cad505860cbf8a507141a74f6d3aaaa9e1c48ea7ccee83ae14135eeb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-16T12:54:13Z","title_canon_sha256":"981c5fa19af49f0c48e872b2f4f3b1e985edeb177f8f8eb1d78ffb7d208ecef0"},"schema_version":"1.0","source":{"id":"2302.08268","kind":"arxiv","version":1}},"canonical_sha256":"eab21558895ec0941e5dc5074f9034b948d5bc85ef7d7b43e9f36339c66fdc63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eab21558895ec0941e5dc5074f9034b948d5bc85ef7d7b43e9f36339c66fdc63","first_computed_at":"2026-07-05T05:42:36.219464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:36.219464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/0xEoUU9wJ4R18tbWAvb2s77eUYlCYLIjivi4zT/LikHEHR3xAChVIF6QDjblyDVWdpHG6Y2x1+gJYzdvhEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:36.219894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60447171100e63c91f1d793c80ebe61d21efba7b17c724616d26139d54721674","sha256:d22ff0ae5fe4d9cafaf95351d8a5fd2a0f5be439122a3bc67fea1c930f01ceea"],"state_sha256":"39add18fb7e63022d372bf15b51622f1973016264c78335777e086af1e72e81e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JqLJb4jcLX83j5CjFlOkm9mLup56dfzkq8vSgY2fzyq1hOeY9loxvjOSGeMtvGIyU52uHvU/C2VU6ci6W/FuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:37:28.769646Z","bundle_sha256":"9336db41b07850fb6daa4ad15cdae27614ea9aa706b5cb80b936571ee550440d"}}